Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

Cardiology Cardiology

Automatic reorientation by deep learning to generate short-axis SPECT myocardial perfusion images.

In Journal of nuclear cardiology : official publication of the American Society of Nuclear Cardiology

BACKGROUND : Single photon emission computed tomography (SPECT) myocardial perfusion images (MPI) can be displayed both in traditional short-axis (SA) cardiac planes and polar maps for interpretation and quantification. It is essential to reorient the reconstructed transaxial SPECT MPI into standard SA slices. This study is aimed to develop a deep-learning-based approach for automatic reorientation of MPI.

METHODS : A total of 254 patients were enrolled, including 226 stress SPECT MPIs and 247 rest SPECT MPIs. Fivefold cross-validation with 180 stress and 201 rest MPIs was used for training and internal validation; the remaining images were used for testing. The rigid transformation parameters (translation and rotation) from manual reorientation were annotated by an experienced nuclear cardiologist and used as the reference standard. A convolutional neural network (CNN) was designed to predict the transformation parameters. Then, the derived transform was applied to the grid generator and sampler in spatial transformer network (STN) to generate the reoriented image. A loss function containing mean absolute errors for translation and mean square errors for rotation was employed. A three-stage optimization strategy was adopted for model optimization: (1) optimize the translation parameters while fixing the rotation parameters; (2) optimize rotation parameters while fixing the translation parameters; (3) optimize both translation and rotation parameters together.

RESULTS : In the test set, the Spearman determination coefficients of the translation distances and rotation angles between the model prediction and the reference standard were 0.993 in X axis, 0.992 in Y axis, 0.994 in Z axis, 0.987 along X axis, 0.990 along Y axis and 0.996 along Z axis, respectively. For the 46 stress MPIs in the test set, the Spearman determination coefficients were 0.858 in percentage of profusion defect (PPD) and 0.858 in summed stress score (SSS); for the 46 rest MPIs in the test set, the Spearman determination coefficients were 0.9 in PPD and 0.9 in summed rest score (SRS).

CONCLUSIONS : Our deep learning-based LV reorientation method is able to accurately generate the SA images. Technical validations and subsequent evaluations of measured clinical parameters show that it has great promise for clinical use.

Zhu Fubao, Wang Guojie, Zhao Chen, Malhotra Saurabh, Zhao Min, He Zhuo, Shi Jianzhou, Jiang Zhixin, Zhou Weihua

2023-Mar-01

SPECT MPI, convolutional neural networks, deep learning, reorientation

General General

Sub-continental-scale carbon stocks of individual trees in African drylands.

In Nature ; h5-index 368.0

The distribution of dryland trees and their density, cover, size, mass and carbon content are not well known at sub-continental to continental scales1-14. This information is important for ecological protection, carbon accounting, climate mitigation and restoration efforts of dryland ecosystems15-18. We assessed more than 9.9 billion trees derived from more than 300,000 satellite images, covering semi-arid sub-Saharan Africa north of the Equator. We attributed wood, foliage and root carbon to every tree in the 0-1,000 mm year-1 rainfall zone by coupling field data19, machine learning20-22, satellite data and high-performance computing. Average carbon stocks of individual trees ranged from 0.54 Mg C ha-1 and 63 kg C tree-1 in the arid zone to 3.7 Mg C ha-1 and 98 kg tree-1 in the sub-humid zone. Overall, we estimated the total carbon for our study area to be 0.84 (±19.8%) Pg C. Comparisons with 14 previous TRENDY numerical simulation studies23 for our area found that the density and carbon stocks of scattered trees have been underestimated by three models and overestimated by 11 models, respectively. This benchmarking can help understand the carbon cycle and address concerns about land degradation24-29. We make available a linked database of wood mass, foliage mass, root mass and carbon stock of each tree for scientists, policymakers, dryland-restoration practitioners and farmers, who can use it to estimate farmland tree carbon stocks from tablets or laptops.

Tucker Compton, Brandt Martin, Hiernaux Pierre, Kariryaa Ankit, Rasmussen Kjeld, Small Jennifer, Igel Christian, Reiner Florian, Melocik Katherine, Meyer Jesse, Sinno Scott, Romero Eric, Glennie Erin, Fitts Yasmin, Morin August, Pinzon Jorge, McClain Devin, Morin Paul, Porter Claire, Loeffler Shane, Kergoat Laurent, Issoufou Bil-Assanou, Savadogo Patrice, Wigneron Jean-Pierre, Poulter Benjamin, Ciais Philippe, Kaufmann Robert, Myneni Ranga, Saatchi Sassan, Fensholt Rasmus

2023-Mar

General General

Radar-based human activity recognition with adaptive thresholding towards resource constrained platforms.

In Scientific reports ; h5-index 158.0

Radar systems are increasingly being employed in healthcare applications for human activity recognition due to their advantages in terms of privacy, contactless sensing, and insensitivity to lighting conditions. The proposed classification algorithms are however often complex, focusing on a single domain of radar, and requiring significant computational resources that prevent their deployment in embedded platforms which often have limited memory and computational resources. To address this issue, we present an adaptive magnitude thresholding approach for highlighting the region of interest in the multi-domain micro-Doppler signatures. The region of interest is beneficial to extract salient features, meanwhile it ensures the simplicity of calculations with less computational cost. The results for the proposed approach show an accuracy of up to 93.1% for six activities, outperforming state-of-the-art deep learning methods on the same dataset with an over tenfold reduction in both training time and memory footprint, and a twofold reduction in inference time compared to a series of deep learning implementations. These results can help bridge the gap toward embedded platform deployment.

Li Zhenghui, Le Kernec Julien, Abbasi Qammer, Fioranelli Francesco, Yang Shufan, Romain Olivier

2023-Mar-01

General General

Abnormal cerebellum connectivity patterns related to motor subtypes of Parkinson's disease.

In Journal of neural transmission (Vienna, Austria : 1996)

Cerebellar dysfunction may substantially contribute to the clinical symptoms of Parkinson's disease (PD). The role of cerebellar subregions in tremors and gait disturbances in PD remains unknown. To investigate alterations in cerebellar subregion volumes and functional connectivity (FC), as well as FC between the dentate nucleus (DN) and ventral lateral posterior nucleus (VLp) of the thalamus, which are potentially involved in different PD motor subtypes. We conducted morphometric and resting-state functional connectivity analyses in various cerebellar subregions in 22 tremor-dominant (TD)-PD and 35 postural instability gait difficulty dominant (PIGD)-PD patients and 38 sex- and age-matched healthy controls (HCs). The volume and FC alterations in various cerebellar subregions and the neural correlates of these changes with the clinical severity scores were investigated. The PIGD-PD group showed greater FC between the right motor cerebellum (CBMm) and left postcentral gyrus than the HC group, and a higher FC was associated with less severe PIGD symptoms. In contrast, the TD-PD group had decreased FC between the right DN and left VLp compared with the PIGD-PD and HC groups, and lower FC was associated with worse TD symptoms. Furthermore, the PIGD-PD group had higher FC between the left DN and left inferior temporal gyrus than the TD-PD group. Morphometric analysis revealed that the TD-PD group showed a significantly higher volume of left CBMm than the HC group. Our findings point to differential alteration patterns in cerebellar subregions and offer a new perspective on the pathophysiology of motor subtypes of PD.

Chen Zhenzhen, He Chentao, Zhang Piao, Cai Xin, Huang Wenlin, Chen Xi, Xu Mingze, Wang Lijuan, Zhang Yuhu

2023-Mar-01

Cerebellar volume, Functional connectivity, Neural correlates, Parkinson’s disease subtype

Radiology Radiology

Comparative validation of AI and non-AI methods in MRI volumetry to diagnose Parkinsonian syndromes.

In Scientific reports ; h5-index 158.0

Automated segmentation and volumetry of brain magnetic resonance imaging (MRI) scans are essential for the diagnosis of Parkinson's disease (PD) and Parkinson's plus syndromes (P-plus). To enhance the diagnostic performance, we adopt deep learning (DL) models in brain MRI segmentation and compared their performance with the gold-standard non-DL method. We collected brain MRI scans of healthy controls ([Formula: see text]) and patients with PD ([Formula: see text]), multiple systemic atrophy ([Formula: see text]), and progressive supranuclear palsy ([Formula: see text]) at Samsung Medical Center from January 2017 to December 2020. Using the gold-standard non-DL model, FreeSurfer (FS), we segmented six brain structures: midbrain, pons, caudate, putamen, pallidum, and third ventricle, and considered them as annotated data for DL models, the representative convolutional neural network (CNN) and vision transformer (ViT)-based models. Dice scores and the area under the curve (AUC) for differentiating normal, PD, and P-plus cases were calculated to determine the measure to which FS performance can be reproduced as-is while increasing speed by the DL approaches. The segmentation times of CNN and ViT for the six brain structures per patient were 51.26 ± 2.50 and 1101.82 ± 22.31 s, respectively, being 14 to 300 times faster than FS (15,735 ± 1.07 s). Dice scores of both DL models were sufficiently high (> 0.85) so their AUCs for disease classification were not inferior to that of FS. For classification of normal vs. P-plus and PD vs. P-plus (except multiple systemic atrophy - Parkinsonian type) based on all brain parts, the DL models and FS showed AUCs above 0.8, demonstrating the clinical value of DL models in addition to FS. DL significantly reduces the analysis time without compromising the performance of brain segmentation and differential diagnosis. Our findings may contribute to the adoption of DL brain MRI segmentation in clinical settings and advance brain research.

Song Joomee, Hahm Juyoung, Lee Jisoo, Lim Chae Yeon, Chung Myung Jin, Youn Jinyoung, Cho Jin Whan, Ahn Jong Hyeon, Kim Kyungsu

2023-Mar-01

General General

Prediction of transition state structures of gas-phase chemical reactions via machine learning.

In Nature communications ; h5-index 260.0

The elucidation of transition state (TS) structures is essential for understanding the mechanisms of chemical reactions and exploring reaction networks. Despite significant advances in computational approaches, TS searching remains a challenging problem owing to the difficulty of constructing an initial structure and heavy computational costs. In this paper, a machine learning (ML) model for predicting the TS structures of general organic reactions is proposed. The proposed model derives the interatomic distances of a TS structure from atomic pair features reflecting reactant, product, and linearly interpolated structures. The model exhibits excellent accuracy, particularly for atomic pairs in which bond formation or breakage occurs. The predicted TS structures yield a high success ratio (93.8%) for quantum chemical saddle point optimizations, and 88.8% of the optimization results have energy errors of less than 0.1 kcal mol-1. Additionally, as a proof of concept, the exploration of multiple reaction paths of an organic reaction is demonstrated based on ML inferences. I envision that the proposed approach will aid in the construction of initial geometries for TS optimization and reaction path exploration.

Choi Sunghwan

2023-Mar-01